8099 search results - page 304 / 1620 » Higher-Order Task Models |
239
click to vote
ML
2002
ACM
15 years 6 months ago
2002
ACM
We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...
187
click to vote
ADAEUROPE
2010
Springer
15 years 4 months ago
2010
Springer
Real-Time (RT) systems exhibit specific characteristics that make them particularly sensitive to architectural decissions. Design patterns help integrating the desired timing behav...
174
click to vote
JMLR
2010
15 years 1 months ago
2010
Supervised learning from multiple labeling sources is an increasingly important problem in machine learning and data mining. This paper develops a probabilistic approach to this p...
172
click to vote
ACL
2012
13 years 9 months ago
2012
We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeli...
156
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...